© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 22794
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icznych
    -0.08
    -object
    -0.07
    osmos
    -0.07
    onj
    -0.07
     wym
    -0.07
     대
    -0.07
    င္း
    -0.07
    -db
    -0.07
    iseach
    -0.07
     Facts
    -0.07
    POSITIVE LOGITS
     сертифик
    0.09
     certificates
    0.08
     určit
    0.08
    ắp
    0.08
    _CERT
    0.08
     tiên
    0.08
     незалеж
    0.08
     marked
    0.08
     herstellen
    0.08
     completar
    0.08
    Activations Density 0.000%

    No Known Activations